Course Content

• Python (Cambridge Spark focuses on the use of Python)¹
• Data privacy, ethics and regulations
• Data visualisations (mainly done in Python)
• Power BI & Tableau (optional)
• Databases & SQL²

Course Content (continued)

• Why data science is good for businesses
• Maths for data science
• Time series analysis
• Descriptive, Predictive and Prescriptive analytics
  • Inferential analysis
• Introduction to machine learning
  • Predictive analysis e.g. forecasting and categorization
• Text-mining, JSON and APIs

Knowledge, Skills and Behaviours (KSBs)

• Two separate sets: one set has to be demonstrated across your portfolio, one has to be demonstrated during your EPA project
• Knowledge: current legislation, data types, principles of statistics & different types of analytics
• Skills: apply statistical methodologies, convert data into visualisations, assess the impact of user experience
• Behaviours: demonstrate initiative and resilience, work independently and collaboratively

The Data Analysis Life Cycle

Timeline & Commitment

• Approximately 16 months from the introductory webinar to the End Point Assessment
• Typically 3 projects that form a portfolio of work + 1 End Point Assessment project
• “Off The Job” hours: minimum 6 hours per week.
• The End Point Assessment
  • A professional discussion focusing on your portfolio
  • A presentation on your End Point Assessment project
  • Questions about your End Point Assessment project

Projects that I undertook

• Automation of data processing for the Non-Bedded Community Modelling Tool
• Improving visualisations for the HIOW Mental Health S136 report
• Exploration of forecasting methods applied to cancer waiting times data
• Using regression to predict improvement in Mental Health PROMs scores
• Investigating the relationship between health inequalities factors on Adult Social Care waiting times, and those waiting times on Emergency Department attendances

What I have done since

• Contributed to the running of Code Club
• Developed a Python script that searches Outlook and downloads attachments
• Supported testing Fabric as a platform for hosting data science projects by creating test machine learning workflows
• Wrote Python webscraping and data concatenation scripts to speed up data processing on a number of projects.
• Overlaid Fingertips data onto maps to support preliminary investigations for a Transformation & Consultancy project.

Reflections

• Keep the Data Analysis Life Cycle in mind for all your projects
• Have the list of KSBs open when you are scoping and writing up your projects
• Stay focused on the STAR method when writing up your portfolio projects
  • Situation
  • Task
  • Action
  • Result